# 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos

arXiv: https://arxiv.org/abs/2103.06498 · HTML: https://mlsanity.com/paper/2103.06498/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 73 references that are in the map.
- First posted on arXiv 11 Mar 2021.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [ReZero is All You Need: Fast Convergence at Large Depth](https://mlsanity.com/paper/2003.04887/) (2020)
- [Video Based Reconstruction of 3D People Models](https://mlsanity.com/paper/1803.04758/) (2018)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation](https://mlsanity.com/paper/1808.05942/) (2018)

## Built on by (most cited first, 26 of 26)

- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [3D Human Texture Estimation from a Single Image with Transformers](https://mlsanity.com/paper/2109.02563/) (2021)
- [LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds](https://mlsanity.com/paper/2203.14698/) (2022)
- [SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Image](https://mlsanity.com/paper/2309.01855/) (2023)
- [Tracking People with 3D Representations](https://mlsanity.com/paper/2111.07868/) (2021)
- [TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generation](https://mlsanity.com/paper/2403.12906/) (2024)
- [VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space](https://mlsanity.com/paper/2312.08291/) (2023)
- [Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images](https://mlsanity.com/paper/2111.01884/) (2021)
- [Low Complexity Channel estimation with Neural Network Solutions](https://mlsanity.com/paper/2201.09934/) (2022)
- [ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image](https://mlsanity.com/paper/2403.10357/) (2024)
- [SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation](https://mlsanity.com/paper/2404.15276/) (2024)
- [Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks](https://mlsanity.com/paper/2305.00936/) (2023)
- [Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction](https://mlsanity.com/paper/2308.00799/) (2023)
- [Super-resolution 3D Human Shape from a Single Low-Resolution Image](https://mlsanity.com/paper/2208.10738/) (2022)
- [Enhancing Egocentric 3D Pose Estimation with Third Person Views](https://mlsanity.com/paper/2201.02017/) (2022)
- [MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing](https://mlsanity.com/paper/2509.23635/) (2025)
- [DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video](https://mlsanity.com/paper/2508.12644/) (2025)
- [Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation](https://mlsanity.com/paper/2202.03074/) (2022)
- [Refining 3D Human Texture Estimation from a Single Image](https://mlsanity.com/paper/2303.03471/) (2023)
- [3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training](https://mlsanity.com/paper/2106.04274/) (2021)
- [EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors](https://mlsanity.com/paper/2306.09615/) (2023)
- [Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos](https://mlsanity.com/paper/2210.03659/) (2022)
- [Generalizable Person Re-Identification via Viewpoint Alignment and Fusion](https://mlsanity.com/paper/2212.02398/) (2022)
- [Revisiting the Role of Texture in 3D Person Re-identification](https://mlsanity.com/paper/2410.00348/) (2024)
- [EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation](https://mlsanity.com/paper/2604.19105/) (2026)
- [Beyond Appearance: A Multi-cue Framework and Large-scale Benchmark for Pedestrian Association and Tracking on Mobile Aerial-Ground Platforms](https://mlsanity.com/paper/2607.23803/) (2026)

## Abstract (arXiv)

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many scenarios such as video surveillance and sports broadcasting. Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. The self-supervision loss enforces scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new losses provide robustness when learning in a weakly-supervised manner. Moreover, we extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images.